In [1]:
import json
import copy
import time
import random
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt
from matplotlib import pyplot as plt
from torchsummary import summary
In [2]:
from nmfd_gnn import NMFD_GNN

1: set parameters¶

In [3]:
print (torch.cuda.is_available())
device = torch.device("cuda:0")
random_seed = 42
random.seed(random_seed)
torch.manual_seed(random_seed)
torch.cuda.manual_seed(random_seed)
r = random.random
True
In [4]:
#1.1: settings
M = 10                       #number of time interval in a window
missing_ratio = 0.50
file_name = "m_" + str(M) + "_missing_" + str(int(missing_ratio*100))
print (file_name)

#1.2: hyperparameters
num_epochs, batch_size, learning_rate = 200, 16, 0.001
beta_flow, beta_occ, beta_phy = 1.0, 1.0, 0.1
batch_size_vt = 16  #batch size for evaluation and test

hyper = {"n_e": num_epochs, "b_s": batch_size, "b_s_vt": batch_size_vt, "l_r": learning_rate,\
         "beta_f": beta_flow, "beta_o": beta_occ, "beta_p": beta_phy}

gnn_dim_1, gnn_dim_2, gnn_dim_3, lstm_dim = 2, 128, 128, 128
p_dim = 10    #column dimension of L1, L2
c_k = 5.5     #meter, the sum of loop width and uniform vehicle length. based on Gero and Daganzo 2008.
theta_ini = [-2.757, 4.996, -2.409, 1.638, 3.569] 

hyper_model = {"g_dim_1": gnn_dim_1, "g_dim_2": gnn_dim_2, "g_dim_3": gnn_dim_3, "l_dim": lstm_dim,\
               "p_dim": p_dim, "c_k": c_k, "theta_ini": theta_ini}
max_no_decrease = 30

#1.3: set paths
root_path = "/home/umni2/a/umnilab/users/xue120/umni4/2023_mfd_traffic/"
file_path = root_path + "2_prepare_data/" + file_name + "/"
train_path, vali_path, test_path =\
    file_path + "train.json", file_path + "vali.json", file_path + "test.json"
sensor_id_path = file_path + "sensor_id_order.json"
sensor_adj_path = file_path + "sensor_adj.json"
mean_std_path = file_path + "mean_std.json"
m_10_missing_50

2: visualization¶

In [5]:
def visualize_train_loss(total_phy_flow_occ_loss):
    plt.figure(figsize=(4,3), dpi=75)
    t_p_f_o_l = np.array(total_phy_flow_occ_loss)
    e_loss, p_loss, f_loss, o_loss = t_p_f_o_l[:,0], t_p_f_o_l[:,1], t_p_f_o_l[:,2], t_p_f_o_l[:,3]
    x = range(len(e_loss))
    plt.plot(x, p_loss, linewidth=1, label = "phy loss")
    plt.plot(x, f_loss, linewidth=1, label = "flow loss")
    plt.plot(x, o_loss, linewidth=1, label = "occ loss")
    plt.legend()
    plt.title('Loss decline on train')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.savefig(file_name + '/' + 'train_loss.png', bbox_inches = 'tight')
    plt.show()
    
def visualize_flow_loss(vali_f_mae, test_f_mae):
    plt.figure(figsize=(4,3), dpi=75)
    x = range(len(vali_f_mae))    
    plt.plot(x, vali_f_mae, linewidth=1, label="Validate")
    plt.plot(x, test_f_mae, linewidth=1, label="Test")
    plt.legend()
    plt.title('MAE of flow on validate/test')
    plt.xlabel('Epoch')
    plt.ylabel('MAE (veh/h)')
    plt.savefig(file_name + '/' + 'flow_mae.png', bbox_inches = 'tight')
    plt.show()
    
def visualize_occ_loss(vali_o_mae, test_o_mae):
    plt.figure(figsize=(4,3), dpi=75)
    x = range(len(vali_o_mae))    
    plt.plot(x, vali_o_mae, linewidth=1, label="Validate")
    plt.plot(x, test_o_mae, linewidth=1, label="Test")
    plt.legend()
    plt.title('MAE of occupancy on validate/test')
    plt.xlabel('Epoch')
    plt.ylabel('MAE')
    plt.savefig(file_name + '/' + 'occ_mae.png',bbox_inches = 'tight')
    plt.show()

3: compute the error¶

In [6]:
def MAELoss(yhat, y):
    return float(torch.mean(torch.div(torch.abs(yhat-y), 1)))

def RMSELoss(yhat, y):
    return float(torch.sqrt(torch.mean((yhat-y)**2)))

def vali_test(model, f, f_mask, o, o_mask, f_o_mean_std, b_s_vt):    
    flow_std, occ_std, n = f_o_mean_std[1], f_o_mean_std[3], len(f)
    f_mae_list, f_rmse_list, o_mae_list, o_rmse_list, num_list = list(), list(), list(), list(), list()
    for i in range(0, n, b_s_vt):
        s, e = i, np.min([i+b_s_vt, n])
        num_list.append(e-s)
        bf, bo, bf_mask, bo_mask = f[s: e], o[s: e], f_mask[s: e], o_mask[s: e]  
        bf_hat, bo_hat, bq_hat, bq_theta = model.run(bf_mask, bo_mask)
        bf_hat, bo_hat = bf_hat.cpu(), bo_hat.cpu()
        bf_mae, bf_rmse = MAELoss(bf_hat, bf)*flow_std, RMSELoss(bf_hat, bf)*flow_std
        bo_mae, bo_rmse = MAELoss(bo_hat, bo)*occ_std, RMSELoss(bo_hat, bo)*occ_std
        f_mae_list.append(bf_mae)
        f_rmse_list.append(bf_rmse)
        o_mae_list.append(bo_mae)
        o_rmse_list.append(bo_rmse)
    f_mae, o_mae = np.dot(f_mae_list, num_list)/n, np.dot(o_mae_list, num_list)/n
    f_rmse = np.sqrt(np.dot(np.multiply(f_rmse_list, f_rmse_list), num_list)/n)
    o_rmse = np.sqrt(np.dot(np.multiply(o_rmse_list, o_rmse_list), num_list)/n)
    return f_mae, f_rmse, o_mae, o_rmse

def evaluate(model, vt_f, vt_o, vt_f_m, vt_o_m, f_o_mean_std, b_s_vt): #vt: vali_test
    vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse  =\
         vali_test(model, vt_f, vt_f_m, vt_o, vt_o_m, f_o_mean_std, b_s_vt)
    return vt_f_mae, vt_f_rmse, vt_o_mae, vt_o_rmse

4: train¶

In [7]:
#4.1: one training epoch
def train_epoch(model, opt, criterion, train_f_x, train_f_y, train_o_x, train_o_y, hyper, flow_std_squ): 
    #f: flow; o: occupancy
    model.train()
    losses, p_losses, f_losses, o_losses = list(), list(), list(), list()
    
    beta_f, beta_o, beta_p, b_s = hyper["beta_f"], hyper["beta_o"], hyper["beta_p"], hyper["b_s"]
    n = len(train_f_x)
    print ("# batch: ", int(n/b_s))   
    
    for i in range(0, n-b_s, b_s):
        time1 = time.time()
        x_f_batch, y_f_batch = train_f_x[i: i+b_s], train_f_y[i: i+b_s]   
        x_o_batch, y_o_batch = train_o_x[i: i+b_s], train_o_y[i: i+b_s]

        opt.zero_grad() 
        y_f_hat, y_o_hat, q_hat, q_theta = model.run(x_f_batch, x_o_batch)
        
        p_loss = criterion(q_hat, q_theta).cpu()                #physical loss 
        p_loss = p_loss/flow_std_squ
        
        f_loss = criterion(y_f_hat.cpu(), y_f_batch)              #data loss of flow
        o_loss = criterion(y_o_hat.cpu(), y_o_batch)              #data loss of occupancy
        
        loss = beta_f*f_loss + beta_o*o_loss + beta_p*p_loss
        
        loss.backward()
        opt.step()
        losses.append(loss.data.numpy())
        p_losses.append(p_loss.data.numpy())
        f_losses.append(f_loss.data.numpy())
        o_losses.append(o_loss.data.numpy())
        
        if i % (64*b_s) == 0:
            print ("i_batch: ", i/b_s)
            print ("the loss for this batch: ", loss.data.numpy())
            print ("flow loss", f_loss.data.numpy())
            print ("occ loss", o_loss.data.numpy())
            time2 = time.time()
            print ("time for this batch", time2-time1)
            print ("----------------------------------")
        n_loss = float(len(losses)+0.000001)
        aver_loss = sum(losses)/n_loss
        aver_p_loss = sum(p_losses)/n_loss
        aver_f_loss = sum(f_losses)/n_loss
        aver_o_loss = sum(o_losses)/n_loss
    return aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss

#4.2: all train epochs
def train_process(model, criterion, train, vali, test, hyper, f_o_mean_std):
    total_phy_flow_occ_loss = list()
    
    n_mse_flow_occ = 0 #mse(flow) + mse(occ) for validation sets.
    
    vali_f, vali_o = vali["flow"], vali["occupancy"] 
    vali_f_m, vali_o_m = vali["flow_mask"].to(device), vali["occupancy_mask"].to(device) 
    test_f, test_o = test["flow"], test["occupancy"] 
    test_f_m, test_o_m = test["flow_mask"].to(device), test["occupancy_mask"].to(device) 
    
    l_r, n_e = hyper["l_r"], hyper["n_e"]
    opt = optim.Adam(model.parameters(), l_r, betas = (0.9,0.999), weight_decay=0.0001)
    opt_scheduler = torch.optim.lr_scheduler.MultiStepLR(opt, milestones=[150])
    
    print ("# epochs ", n_e)
    r_vali_f_mae, r_vali_o_mae, r_test_f_mae, r_test_o_mae = list(), list(), list(), list()
    r_vali_f_rmse, r_vali_o_rmse, r_test_f_rmse, r_test_o_rmse = list(), list(), list(), list()
    
    flow_std_squ = np.power(f_o_mean_std[1], 2)
    
    no_decrease = 0
    for i in range(n_e):
        print ("----------------an epoch starts-------------------")
        #time1_s = time.time()
        
        time_s = time.time()
        print ("i_epoch: ", i)
        n_train = len(train["flow"])
        number_list = copy.copy(list(range(n_train)))
        random.shuffle(number_list, random = r)
        shuffle_idx = torch.tensor(number_list)
        train_x_f, train_y_f = train["flow_mask"][shuffle_idx], train["flow"][shuffle_idx]
        train_x_o, train_y_o = train["occupancy_mask"][shuffle_idx], train["occupancy"][shuffle_idx] 
        
        
        aver_loss, model, aver_p_loss, aver_f_loss, aver_o_loss =\
            train_epoch(model, opt, criterion, train_x_f.to(device), train_y_f,\
                        train_x_o.to(device), train_y_o, hyper, flow_std_squ)
        opt_scheduler.step()
        
        total_phy_flow_occ_loss.append([aver_loss, aver_p_loss, aver_f_loss, aver_o_loss])
        print ("train loss for this epoch: ", round(aver_loss, 6))
        
        #evaluate
        b_s_vt = hyper["b_s_vt"]
        vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
            evaluate(model, vali_f, vali_o, vali_f_m, vali_o_m, f_o_mean_std, b_s_vt)
        test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
            evaluate(model, test_f, test_o, test_f_m, test_o_m, f_o_mean_std, b_s_vt)  
        
        r_vali_f_mae.append(vali_f_mae)
        r_test_f_mae.append(test_f_mae)
        r_vali_o_mae.append(vali_o_mae)
        r_test_o_mae.append(test_o_mae)
        r_vali_f_rmse.append(vali_f_rmse)
        r_test_f_rmse.append(test_f_rmse)
        r_vali_o_rmse.append(vali_o_rmse)
        r_test_o_rmse.append(test_o_rmse)
        
        visualize_train_loss(total_phy_flow_occ_loss)
        visualize_flow_loss(r_vali_f_mae, r_test_f_mae)
        visualize_occ_loss(r_vali_o_mae, r_test_o_mae)
        time_e = time.time()
        print ("time for this epoch", time_e - time_s)
        
        performance = {"train": total_phy_flow_occ_loss,\
                  "vali": [r_vali_f_mae, r_vali_f_rmse, r_vali_o_mae, r_vali_o_rmse],\
                  "test": [r_test_f_mae, r_test_f_rmse, r_test_o_mae, r_test_o_rmse]}
        subfile =  open(file_name + '/' + 'performance'+'.json','w')
        json.dump(performance, subfile)
        subfile.close()
        
        #early stop
        flow_std, occ_std = f_o_mean_std[1], f_o_mean_std[3]
        norm_f_rmse, norm_o_rmse = vali_f_rmse/flow_std, vali_o_rmse/occ_std
        norm_sum_mse = norm_f_rmse*norm_f_rmse + norm_o_rmse*norm_o_rmse
        
        if n_mse_flow_occ > 0:
            min_until_now = min([min_until_now, norm_sum_mse])
        else:
            min_until_now = 1000000.0  
        if norm_sum_mse > min_until_now:
            no_decrease = no_decrease+1
        else:
            no_decrease = 0
        if no_decrease == max_no_decrease:
            print ("Early stop at the " + str(i+1) + "-th epoch")
            return total_phy_flow_occ_loss, model 
        n_mse_flow_occ = n_mse_flow_occ + 1
        
        print ("No_decrease: ", no_decrease)
    return total_phy_flow_occ_loss, model    

5: prepare tensors¶

In [8]:
def tensorize(train_vali_test):
    result = dict()
    result["flow"] = torch.tensor(train_vali_test["flow"]) 
    result["flow_mask"] = torch.tensor(train_vali_test["flow_mask"])     
    result["occupancy"] = torch.tensor(train_vali_test["occupancy"]) 
    result["occupancy_mask"] = torch.tensor(train_vali_test["occupancy_mask"]) 
    return result

def normalize_flow_occ(tvt, f_o_mean_std):  #tvt: train, vali, test
    #flow
    f_mean, f_std = f_o_mean_std[0], f_o_mean_std[1]
    f_mask, f = tvt["flow_mask"], tvt["flow"]
    tvt["flow_mask"] = ((np.array(f_mask)-f_mean)/f_std).tolist()
    tvt["flow"] = ((np.array(f)-f_mean)/f_std).tolist()
    
    #occ
    o_mean, o_std = f_o_mean_std[2], f_o_mean_std[3]
    o_mask, o = tvt["occupancy_mask"], tvt["occupancy"]
    tvt["occupancy_mask"] = ((np.array(o_mask)-o_mean)/o_std).tolist()
    tvt["occupancy"] = ((np.array(o)-o_mean)/o_std).tolist()   
    return tvt

def transform_distance(d_matrix):
    sigma, n_row, n_col = np.std(d_matrix), len(d_matrix), len(d_matrix[0])
    sigma_square = sigma*sigma
    for i in range(n_row):
        for j in range(n_col):
            d_i_j = d_matrix[i][j]
            d_matrix[i][j] = np.exp(0.0-10000.0*d_i_j*d_i_j/sigma_square)
    return d_matrix

def load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path):
    mean_std = json.load(open(mean_std_path))
    f_mean, f_std, o_mean, o_std =\
        mean_std["f_mean"], mean_std["f_std"], mean_std["o_mean"], mean_std["o_std"]
    f_o_mean_std = [f_mean, f_std, o_mean, o_std]
    
    train = json.load(open(train_path))
    vali = json.load(open(vali_path))
    test = json.load(open(test_path))
    adj = json.load(open(sensor_adj_path))["adj"]
    n_sensor = len(train["flow"][0])    
    
    train = tensorize(normalize_flow_occ(train, f_o_mean_std))
    vali = tensorize(normalize_flow_occ(vali, f_o_mean_std))
    test = tensorize(normalize_flow_occ(test, f_o_mean_std))

    adj = torch.tensor(transform_distance(adj), device=device).float()   
    
    df_sensor_id = json.load(open(sensor_id_path))
    sensor_length = [0.0 for i in range(n_sensor)]
    for sensor in df_sensor_id:
        sensor_length[df_sensor_id[sensor][0]] = df_sensor_id[sensor][3]
        
    return train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length

6: main¶

In [9]:
#6.1 load the data
time1 = time.time()
train, vali, test, adj, n_sensor, f_o_mean_std, sensor_length =\
    load_data(train_path, vali_path, test_path, sensor_adj_path, mean_std_path, sensor_id_path)
time2 = time.time()
print (time2-time1)
10.49973177909851
In [10]:
print (len(train["flow"]))
print (len(vali["flow"]))
print (len(test["flow"]))
print (f_o_mean_std)
2007
663
663
[240.33475289317576, 220.77174415099844, 0.13747677267259475, 0.19174061724441546]
In [11]:
model = NMFD_GNN(n_sensor, M, hyper_model, f_o_mean_std, sensor_length, adj).to(device)   
cri = nn.MSELoss() 
In [12]:
#6.2: train the model
total_phy_flow_occ_loss, trained_model = train_process(model, cri, train, vali, test, hyper, f_o_mean_std)
# epochs  200
----------------an epoch starts-------------------
i_epoch:  0
# batch:  125
i_batch:  0.0
the loss for this batch:  1.959289
flow loss 0.92753893
occ loss 0.9138899
time for this batch 0.4802360534667969
----------------------------------
i_batch:  64.0
the loss for this batch:  0.59473425
flow loss 0.17845821
occ loss 0.29241276
time for this batch 0.25343966484069824
----------------------------------
train loss for this epoch:  0.737723
time for this epoch 38.00006556510925
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  1
# batch:  125
i_batch:  0.0
the loss for this batch:  0.48059762
flow loss 0.16669507
occ loss 0.21912152
time for this batch 0.19287514686584473
----------------------------------
i_batch:  64.0
the loss for this batch:  0.5157336
flow loss 0.13809633
occ loss 0.23829739
time for this batch 0.2552754878997803
----------------------------------
train loss for this epoch:  0.540192
time for this epoch 36.67076396942139
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  2
# batch:  125
i_batch:  0.0
the loss for this batch:  0.47966182
flow loss 0.14806265
occ loss 0.20590799
time for this batch 0.19881558418273926
----------------------------------
i_batch:  64.0
the loss for this batch:  0.5140161
flow loss 0.13528827
occ loss 0.23756789
time for this batch 0.2600061893463135
----------------------------------
train loss for this epoch:  0.498417
time for this epoch 36.96955418586731
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  3
# batch:  125
i_batch:  0.0
the loss for this batch:  0.4728306
flow loss 0.12299024
occ loss 0.21988808
time for this batch 0.19420742988586426
----------------------------------
i_batch:  64.0
the loss for this batch:  0.58723855
flow loss 0.12599048
occ loss 0.2767636
time for this batch 0.23760199546813965
----------------------------------
train loss for this epoch:  0.476829
time for this epoch 37.592716455459595
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  4
# batch:  125
i_batch:  0.0
the loss for this batch:  0.4706776
flow loss 0.11022968
occ loss 0.23111342
time for this batch 0.19683146476745605
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4324484
flow loss 0.11187602
occ loss 0.21123557
time for this batch 0.2661583423614502
----------------------------------
train loss for this epoch:  0.463017
time for this epoch 38.27885055541992
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  5
# batch:  125
i_batch:  0.0
the loss for this batch:  0.416869
flow loss 0.102207914
occ loss 0.19225225
time for this batch 0.19225478172302246
----------------------------------
i_batch:  64.0
the loss for this batch:  0.64358157
flow loss 0.13315484
occ loss 0.31668878
time for this batch 0.25696682929992676
----------------------------------
train loss for this epoch:  0.453746
time for this epoch 37.85625100135803
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  6
# batch:  125
i_batch:  0.0
the loss for this batch:  0.33180904
flow loss 0.094735734
occ loss 0.15165685
time for this batch 0.21249938011169434
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4602374
flow loss 0.12455013
occ loss 0.21816705
time for this batch 0.25021862983703613
----------------------------------
train loss for this epoch:  0.446921
time for this epoch 37.852065086364746
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  7
# batch:  125
i_batch:  0.0
the loss for this batch:  0.52345604
flow loss 0.12549119
occ loss 0.2584214
time for this batch 0.2016158103942871
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3521286
flow loss 0.0905769
occ loss 0.15607712
time for this batch 0.26697230339050293
----------------------------------
train loss for this epoch:  0.441621
time for this epoch 37.59002494812012
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  8
# batch:  125
i_batch:  0.0
the loss for this batch:  0.39308792
flow loss 0.108682245
occ loss 0.179894
time for this batch 0.21093010902404785
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2919426
flow loss 0.08452475
occ loss 0.13565709
time for this batch 0.24441909790039062
----------------------------------
train loss for this epoch:  0.439042
time for this epoch 36.16402554512024
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  9
# batch:  125
i_batch:  0.0
the loss for this batch:  0.54956466
flow loss 0.119372636
occ loss 0.28348154
time for this batch 0.2553231716156006
----------------------------------
i_batch:  64.0
the loss for this batch:  0.46013403
flow loss 0.10121702
occ loss 0.22720988
time for this batch 0.2712819576263428
----------------------------------
train loss for this epoch:  0.433369
time for this epoch 45.21177339553833
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  10
# batch:  125
i_batch:  0.0
the loss for this batch:  0.4187125
flow loss 0.09432088
occ loss 0.22096041
time for this batch 0.2601170539855957
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2643367
flow loss 0.06935189
occ loss 0.118046895
time for this batch 0.2931089401245117
----------------------------------
train loss for this epoch:  0.429429
time for this epoch 46.646819829940796
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  11
# batch:  125
i_batch:  0.0
the loss for this batch:  0.3350133
flow loss 0.098184235
occ loss 0.14688812
time for this batch 0.2669343948364258
----------------------------------
i_batch:  64.0
the loss for this batch:  0.45446497
flow loss 0.097052634
occ loss 0.22411409
time for this batch 0.2885136604309082
----------------------------------
train loss for this epoch:  0.427147
time for this epoch 45.65103030204773
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  12
# batch:  125
i_batch:  0.0
the loss for this batch:  0.33135796
flow loss 0.082647264
occ loss 0.15924092
time for this batch 0.26223230361938477
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4445315
flow loss 0.10487986
occ loss 0.20875265
time for this batch 0.29975390434265137
----------------------------------
train loss for this epoch:  0.423688
time for this epoch 47.46991491317749
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  13
# batch:  125
i_batch:  0.0
the loss for this batch:  0.5714424
flow loss 0.11036717
occ loss 0.28938106
time for this batch 0.27007484436035156
----------------------------------
i_batch:  64.0
the loss for this batch:  0.37835303
flow loss 0.09338489
occ loss 0.17357412
time for this batch 0.2828230857849121
----------------------------------
train loss for this epoch:  0.419905
time for this epoch 46.905152320861816
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  14
# batch:  125
i_batch:  0.0
the loss for this batch:  0.42740804
flow loss 0.083769955
occ loss 0.21176513
time for this batch 0.2709805965423584
----------------------------------
i_batch:  64.0
the loss for this batch:  0.5046829
flow loss 0.10940559
occ loss 0.24537106
time for this batch 0.29168128967285156
----------------------------------
train loss for this epoch:  0.416588
time for this epoch 47.52523732185364
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  15
# batch:  125
i_batch:  0.0
the loss for this batch:  0.42384195
flow loss 0.10045713
occ loss 0.18276428
time for this batch 0.26361608505249023
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4878999
flow loss 0.09112033
occ loss 0.23374093
time for this batch 0.3021352291107178
----------------------------------
train loss for this epoch:  0.417718
time for this epoch 47.66518020629883
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  16
# batch:  125
i_batch:  0.0
the loss for this batch:  0.39250967
flow loss 0.08170666
occ loss 0.19030109
time for this batch 0.26232481002807617
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3917481
flow loss 0.0891511
occ loss 0.18132964
time for this batch 0.28710198402404785
----------------------------------
train loss for this epoch:  0.411625
time for this epoch 47.221314907073975
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  17
# batch:  125
i_batch:  0.0
the loss for this batch:  0.4230513
flow loss 0.08667917
occ loss 0.22745931
time for this batch 0.2687854766845703
----------------------------------
i_batch:  64.0
the loss for this batch:  0.34618765
flow loss 0.08897135
occ loss 0.14056604
time for this batch 0.2840456962585449
----------------------------------
train loss for this epoch:  0.409476
time for this epoch 46.65033435821533
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  18
# batch:  125
i_batch:  0.0
the loss for this batch:  0.35983163
flow loss 0.07884595
occ loss 0.16964246
time for this batch 0.2624506950378418
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3364085
flow loss 0.08321754
occ loss 0.14889129
time for this batch 0.2702476978302002
----------------------------------
train loss for this epoch:  0.409824
time for this epoch 47.45305109024048
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  19
# batch:  125
i_batch:  0.0
the loss for this batch:  0.46267447
flow loss 0.09937463
occ loss 0.21798404
time for this batch 0.2614743709564209
----------------------------------
i_batch:  64.0
the loss for this batch:  0.29497832
flow loss 0.06835397
occ loss 0.13864315
time for this batch 0.2990109920501709
----------------------------------
train loss for this epoch:  0.407845
time for this epoch 47.504754304885864
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  20
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2915889
flow loss 0.068661
occ loss 0.13700469
time for this batch 0.2632486820220947
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2902813
flow loss 0.07092147
occ loss 0.12926641
time for this batch 0.28574609756469727
----------------------------------
train loss for this epoch:  0.40546
time for this epoch 47.56872272491455
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  21
# batch:  125
i_batch:  0.0
the loss for this batch:  0.49788767
flow loss 0.120698765
occ loss 0.23262958
time for this batch 0.25696611404418945
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3943981
flow loss 0.08965141
occ loss 0.17682514
time for this batch 0.2933979034423828
----------------------------------
train loss for this epoch:  0.403744
time for this epoch 47.80527949333191
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  22
# batch:  125
i_batch:  0.0
the loss for this batch:  0.44866592
flow loss 0.0998876
occ loss 0.22185567
time for this batch 0.2718372344970703
----------------------------------
i_batch:  64.0
the loss for this batch:  0.34530193
flow loss 0.07492229
occ loss 0.15192437
time for this batch 0.29611968994140625
----------------------------------
train loss for this epoch:  0.40274
time for this epoch 47.01766610145569
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  23
# batch:  125
i_batch:  0.0
the loss for this batch:  0.418509
flow loss 0.102042794
occ loss 0.19274949
time for this batch 0.24262666702270508
----------------------------------
i_batch:  64.0
the loss for this batch:  0.31785348
flow loss 0.07883911
occ loss 0.13997953
time for this batch 0.2655925750732422
----------------------------------
train loss for this epoch:  0.400665
time for this epoch 47.726945638656616
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  24
# batch:  125
i_batch:  0.0
the loss for this batch:  0.3645308
flow loss 0.07810803
occ loss 0.16517538
time for this batch 0.26447153091430664
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4077364
flow loss 0.08778158
occ loss 0.17455779
time for this batch 0.28083109855651855
----------------------------------
train loss for this epoch:  0.398011
time for this epoch 46.70844745635986
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  25
# batch:  125
i_batch:  0.0
the loss for this batch:  0.44503194
flow loss 0.09083409
occ loss 0.21526867
time for this batch 0.2555885314941406
----------------------------------
i_batch:  64.0
the loss for this batch:  0.43556416
flow loss 0.091708556
occ loss 0.18888828
time for this batch 0.2947070598602295
----------------------------------
train loss for this epoch:  0.398497
time for this epoch 47.3539662361145
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  26
# batch:  125
i_batch:  0.0
the loss for this batch:  0.412768
flow loss 0.08878282
occ loss 0.18720919
time for this batch 0.2628636360168457
----------------------------------
i_batch:  64.0
the loss for this batch:  0.31031597
flow loss 0.078314014
occ loss 0.1342267
time for this batch 0.28699183464050293
----------------------------------
train loss for this epoch:  0.395069
time for this epoch 46.965550661087036
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  27
# batch:  125
i_batch:  0.0
the loss for this batch:  0.3067327
flow loss 0.07762797
occ loss 0.1351566
time for this batch 0.2565934658050537
----------------------------------
i_batch:  64.0
the loss for this batch:  0.32832903
flow loss 0.080268584
occ loss 0.14597502
time for this batch 0.2889223098754883
----------------------------------
train loss for this epoch:  0.395264
time for this epoch 46.37427854537964
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  28
# batch:  125
i_batch:  0.0
the loss for this batch:  0.37634522
flow loss 0.08605921
occ loss 0.16860029
time for this batch 0.2674839496612549
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4284904
flow loss 0.10132648
occ loss 0.21117404
time for this batch 0.2874772548675537
----------------------------------
train loss for this epoch:  0.392456
time for this epoch 46.98146724700928
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  29
# batch:  125
i_batch:  0.0
the loss for this batch:  0.4541524
flow loss 0.09205367
occ loss 0.23282531
time for this batch 0.25710344314575195
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4323855
flow loss 0.09292131
occ loss 0.20266278
time for this batch 0.2973668575286865
----------------------------------
train loss for this epoch:  0.392751
time for this epoch 47.455841064453125
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  30
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27439845
flow loss 0.067245804
occ loss 0.122441836
time for this batch 0.26897597312927246
----------------------------------
i_batch:  64.0
the loss for this batch:  0.42500368
flow loss 0.09150826
occ loss 0.20604141
time for this batch 0.2961695194244385
----------------------------------
train loss for this epoch:  0.391515
time for this epoch 47.301703214645386
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  31
# batch:  125
i_batch:  0.0
the loss for this batch:  0.28884265
flow loss 0.07207749
occ loss 0.12557624
time for this batch 0.26438283920288086
----------------------------------
i_batch:  64.0
the loss for this batch:  0.39898837
flow loss 0.08940457
occ loss 0.17881626
time for this batch 0.2889690399169922
----------------------------------
train loss for this epoch:  0.389068
time for this epoch 47.51772880554199
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  32
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23367536
flow loss 0.06489787
occ loss 0.09600489
time for this batch 0.25600171089172363
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3911742
flow loss 0.080996245
occ loss 0.18815048
time for this batch 0.2231278419494629
----------------------------------
train loss for this epoch:  0.389523
time for this epoch 47.594916582107544
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  33
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24039307
flow loss 0.056729022
occ loss 0.10622925
time for this batch 0.2486410140991211
----------------------------------
i_batch:  64.0
the loss for this batch:  0.4404741
flow loss 0.09700682
occ loss 0.19926481
time for this batch 0.2882075309753418
----------------------------------
train loss for this epoch:  0.387316
time for this epoch 47.630085468292236
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  34
# batch:  125
i_batch:  0.0
the loss for this batch:  0.35311344
flow loss 0.07847873
occ loss 0.15382746
time for this batch 0.27048778533935547
----------------------------------
i_batch:  64.0
the loss for this batch:  0.29667008
flow loss 0.07045247
occ loss 0.12802109
time for this batch 0.2643246650695801
----------------------------------
train loss for this epoch:  0.382171
time for this epoch 48.75939750671387
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  35
# batch:  125
i_batch:  0.0
the loss for this batch:  0.46338433
flow loss 0.111042395
occ loss 0.2024792
time for this batch 0.2714364528656006
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2915996
flow loss 0.07199733
occ loss 0.12921262
time for this batch 0.2854917049407959
----------------------------------
train loss for this epoch:  0.376363
time for this epoch 47.250969648361206
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  36
# batch:  125
i_batch:  0.0
the loss for this batch:  0.39998263
flow loss 0.090210475
occ loss 0.19191778
time for this batch 0.26799535751342773
----------------------------------
i_batch:  64.0
the loss for this batch:  0.42443103
flow loss 0.091639824
occ loss 0.19844736
time for this batch 0.30698323249816895
----------------------------------
train loss for this epoch:  0.366044
time for this epoch 47.482481479644775
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  37
# batch:  125
i_batch:  0.0
the loss for this batch:  0.43580437
flow loss 0.096318945
occ loss 0.23350309
time for this batch 0.26986002922058105
----------------------------------
i_batch:  64.0
the loss for this batch:  0.37136889
flow loss 0.09631095
occ loss 0.18298393
time for this batch 0.29846906661987305
----------------------------------
train loss for this epoch:  0.348983
time for this epoch 47.231112480163574
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  38
# batch:  125
i_batch:  0.0
the loss for this batch:  0.296546
flow loss 0.07844511
occ loss 0.14820437
time for this batch 0.2792685031890869
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3505431
flow loss 0.08256437
occ loss 0.19833578
time for this batch 0.29732465744018555
----------------------------------
train loss for this epoch:  0.325556
time for this epoch 47.39773225784302
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  39
# batch:  125
i_batch:  0.0
the loss for this batch:  0.3436501
flow loss 0.08452194
occ loss 0.20034897
time for this batch 0.2533986568450928
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3328058
flow loss 0.09064751
occ loss 0.18051228
time for this batch 0.3079185485839844
----------------------------------
train loss for this epoch:  0.300443
time for this epoch 48.187466859817505
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  40
# batch:  125
i_batch:  0.0
the loss for this batch:  0.28739437
flow loss 0.07468592
occ loss 0.16782029
time for this batch 0.2794830799102783
----------------------------------
i_batch:  64.0
the loss for this batch:  0.28428668
flow loss 0.07583121
occ loss 0.18329133
time for this batch 0.28107285499572754
----------------------------------
train loss for this epoch:  0.275882
time for this epoch 46.405744791030884
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  41
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23770827
flow loss 0.06914614
occ loss 0.14781004
time for this batch 0.248976469039917
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23045835
flow loss 0.06752442
occ loss 0.15258977
time for this batch 0.2850306034088135
----------------------------------
train loss for this epoch:  0.257659
time for this epoch 47.07635474205017
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  42
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23718418
flow loss 0.06734822
occ loss 0.16217753
time for this batch 0.2717440128326416
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2755147
flow loss 0.08132602
occ loss 0.18819109
time for this batch 0.29810357093811035
----------------------------------
train loss for this epoch:  0.247737
time for this epoch 46.57313895225525
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  43
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24539429
flow loss 0.0675629
occ loss 0.17462945
time for this batch 0.25757503509521484
----------------------------------
i_batch:  64.0
the loss for this batch:  0.15256616
flow loss 0.048421364
occ loss 0.10329175
time for this batch 0.2745940685272217
----------------------------------
train loss for this epoch:  0.243441
time for this epoch 46.3897705078125
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  44
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2314665
flow loss 0.06307741
occ loss 0.16744214
time for this batch 0.2849574089050293
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2269302
flow loss 0.061634675
occ loss 0.16420202
time for this batch 0.2658979892730713
----------------------------------
train loss for this epoch:  0.241202
time for this epoch 48.51225018501282
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  45
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21483414
flow loss 0.064058706
occ loss 0.14984004
time for this batch 0.2726607322692871
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27593678
flow loss 0.074824624
occ loss 0.20031178
time for this batch 0.27135443687438965
----------------------------------
train loss for this epoch:  0.240802
time for this epoch 47.41563558578491
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  46
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20039739
flow loss 0.06356265
occ loss 0.1363557
time for this batch 0.3732285499572754
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2798099
flow loss 0.07495467
occ loss 0.20430468
time for this batch 0.2993950843811035
----------------------------------
train loss for this epoch:  0.239247
time for this epoch 48.37431359291077
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  47
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25683767
flow loss 0.078935556
occ loss 0.17718922
time for this batch 0.2692525386810303
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23964356
flow loss 0.06743676
occ loss 0.17182566
time for this batch 0.2926509380340576
----------------------------------
train loss for this epoch:  0.240788
time for this epoch 48.26279950141907
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  48
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26828057
flow loss 0.07082041
occ loss 0.19688798
time for this batch 0.2819225788116455
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22456808
flow loss 0.06732326
occ loss 0.15656507
time for this batch 0.3030202388763428
----------------------------------
train loss for this epoch:  0.239062
time for this epoch 47.69763469696045
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  49
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26636764
flow loss 0.068363175
occ loss 0.19763097
time for this batch 0.2792949676513672
----------------------------------
i_batch:  64.0
the loss for this batch:  0.30866557
flow loss 0.07485457
occ loss 0.2330326
time for this batch 0.29741358757019043
----------------------------------
train loss for this epoch:  0.237271
time for this epoch 47.349812746047974
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  50
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22324823
flow loss 0.069190346
occ loss 0.15355076
time for this batch 0.27197265625
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16664316
flow loss 0.04995643
occ loss 0.116331205
time for this batch 0.2998771667480469
----------------------------------
train loss for this epoch:  0.237935
time for this epoch 48.200422525405884
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  51
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2727035
flow loss 0.07080074
occ loss 0.20134506
time for this batch 0.27256226539611816
----------------------------------
i_batch:  64.0
the loss for this batch:  0.1713831
flow loss 0.04863291
occ loss 0.121698916
time for this batch 0.30940747261047363
----------------------------------
train loss for this epoch:  0.23868
time for this epoch 47.09681558609009
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  52
# batch:  125
i_batch:  0.0
the loss for this batch:  0.13941409
flow loss 0.04215867
occ loss 0.096497305
time for this batch 0.2797548770904541
----------------------------------
i_batch:  64.0
the loss for this batch:  0.29541177
flow loss 0.07510733
occ loss 0.21970639
time for this batch 0.2912898063659668
----------------------------------
train loss for this epoch:  0.237047
time for this epoch 47.35651183128357
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  53
# batch:  125
i_batch:  0.0
the loss for this batch:  0.35284144
flow loss 0.08475338
occ loss 0.26748154
time for this batch 0.27117085456848145
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2690772
flow loss 0.069045715
occ loss 0.19943127
time for this batch 0.30091047286987305
----------------------------------
train loss for this epoch:  0.235417
time for this epoch 48.28002858161926
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  54
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25620937
flow loss 0.067624174
occ loss 0.18801177
time for this batch 0.2547481060028076
----------------------------------
i_batch:  64.0
the loss for this batch:  0.29283845
flow loss 0.0787865
occ loss 0.2133601
time for this batch 0.30998849868774414
----------------------------------
train loss for this epoch:  0.236756
time for this epoch 48.18000411987305
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  55
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24645151
flow loss 0.070007496
occ loss 0.17593475
time for this batch 0.28601861000061035
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23015429
flow loss 0.06356804
occ loss 0.16587488
time for this batch 0.28065013885498047
----------------------------------
train loss for this epoch:  0.235598
time for this epoch 47.7903048992157
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  56
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2139706
flow loss 0.0602513
occ loss 0.15331014
time for this batch 0.2564702033996582
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22260019
flow loss 0.062479157
occ loss 0.15969862
time for this batch 0.30275583267211914
----------------------------------
train loss for this epoch:  0.235903
time for this epoch 47.84366178512573
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  57
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23606679
flow loss 0.06772849
occ loss 0.16757397
time for this batch 0.25382399559020996
----------------------------------
i_batch:  64.0
the loss for this batch:  0.26340023
flow loss 0.070670836
occ loss 0.1922354
time for this batch 0.2918412685394287
----------------------------------
train loss for this epoch:  0.23494
time for this epoch 47.196444034576416
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  58
# batch:  125
i_batch:  0.0
the loss for this batch:  0.29792956
flow loss 0.0783417
occ loss 0.21901394
time for this batch 0.2775444984436035
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21439281
flow loss 0.05808028
occ loss 0.15543032
time for this batch 0.2991909980773926
----------------------------------
train loss for this epoch:  0.234092
time for this epoch 47.8333044052124
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  59
# batch:  125
i_batch:  0.0
the loss for this batch:  0.1880255
flow loss 0.057341736
occ loss 0.13022833
time for this batch 0.25816822052001953
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22843714
flow loss 0.062383436
occ loss 0.16560824
time for this batch 0.29415154457092285
----------------------------------
train loss for this epoch:  0.234417
time for this epoch 47.700819969177246
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  60
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21496017
flow loss 0.065260336
occ loss 0.14898553
time for this batch 0.2677130699157715
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2359712
flow loss 0.06138767
occ loss 0.17422217
time for this batch 0.30955982208251953
----------------------------------
train loss for this epoch:  0.233796
time for this epoch 47.64929723739624
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  61
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24167429
flow loss 0.067171924
occ loss 0.17397927
time for this batch 0.2646932601928711
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18281852
flow loss 0.05205905
occ loss 0.13042518
time for this batch 0.2927844524383545
----------------------------------
train loss for this epoch:  0.235332
time for this epoch 47.76959300041199
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  62
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19509473
flow loss 0.05634137
occ loss 0.1380814
time for this batch 0.2852442264556885
----------------------------------
i_batch:  64.0
the loss for this batch:  0.28213617
flow loss 0.07716885
occ loss 0.20460531
time for this batch 0.3052821159362793
----------------------------------
train loss for this epoch:  0.232735
time for this epoch 48.84825921058655
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  63
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23396996
flow loss 0.061190832
occ loss 0.17203721
time for this batch 0.25554752349853516
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2360678
flow loss 0.07021848
occ loss 0.16518255
time for this batch 0.26607370376586914
----------------------------------
train loss for this epoch:  0.234075
time for this epoch 47.29732322692871
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  64
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25965583
flow loss 0.06890891
occ loss 0.19027618
time for this batch 0.24835205078125
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3050441
flow loss 0.07413155
occ loss 0.23028027
time for this batch 0.2926933765411377
----------------------------------
train loss for this epoch:  0.232585
time for this epoch 47.031018018722534
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  65
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24079485
flow loss 0.063501336
occ loss 0.17678735
time for this batch 0.2697944641113281
----------------------------------
i_batch:  64.0
the loss for this batch:  0.30485502
flow loss 0.07766143
occ loss 0.2267104
time for this batch 0.2855370044708252
----------------------------------
train loss for this epoch:  0.232194
time for this epoch 47.57653856277466
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  66
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17371188
flow loss 0.048919145
occ loss 0.124524325
time for this batch 0.2618741989135742
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2249752
flow loss 0.071370274
occ loss 0.1532133
time for this batch 0.29657721519470215
----------------------------------
train loss for this epoch:  0.23117
time for this epoch 47.13095951080322
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  67
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27005395
flow loss 0.07234163
occ loss 0.19702254
time for this batch 0.27483582496643066
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21530893
flow loss 0.060387347
occ loss 0.15446617
time for this batch 0.2981557846069336
----------------------------------
train loss for this epoch:  0.23207
time for this epoch 46.9542191028595
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  68
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18100055
flow loss 0.051907092
occ loss 0.12857153
time for this batch 0.25880885124206543
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2605554
flow loss 0.06787059
occ loss 0.19211207
time for this batch 0.29389500617980957
----------------------------------
train loss for this epoch:  0.231281
time for this epoch 47.23220944404602
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  69
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18186025
flow loss 0.058224205
occ loss 0.123344466
time for this batch 0.26398396492004395
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16653484
flow loss 0.04572148
occ loss 0.120395884
time for this batch 0.2904846668243408
----------------------------------
train loss for this epoch:  0.231279
time for this epoch 46.98932671546936
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  70
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25979966
flow loss 0.07533515
occ loss 0.18389452
time for this batch 0.2309737205505371
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22767152
flow loss 0.06324739
occ loss 0.1638423
time for this batch 0.2896761894226074
----------------------------------
train loss for this epoch:  0.231288
time for this epoch 47.460524797439575
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  71
# batch:  125
i_batch:  0.0
the loss for this batch:  0.28091475
flow loss 0.07218766
occ loss 0.20804696
time for this batch 0.27445483207702637
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25636625
flow loss 0.0704892
occ loss 0.18506435
time for this batch 0.3061103820800781
----------------------------------
train loss for this epoch:  0.230683
time for this epoch 47.738752126693726
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  72
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25412273
flow loss 0.067727044
occ loss 0.18588501
time for this batch 0.25240373611450195
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23571154
flow loss 0.06349738
occ loss 0.17167677
time for this batch 0.28758931159973145
----------------------------------
train loss for this epoch:  0.230394
time for this epoch 46.38420510292053
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  73
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19833606
flow loss 0.058276743
occ loss 0.13966985
time for this batch 0.26000070571899414
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25358826
flow loss 0.07224694
occ loss 0.18087032
time for this batch 0.28642845153808594
----------------------------------
train loss for this epoch:  0.228942
time for this epoch 47.2062132358551
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  74
# batch:  125
i_batch:  0.0
the loss for this batch:  0.32707146
flow loss 0.08198268
occ loss 0.24460237
time for this batch 0.2936568260192871
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2188846
flow loss 0.06252908
occ loss 0.1559202
time for this batch 0.29698920249938965
----------------------------------
train loss for this epoch:  0.230326
time for this epoch 46.67064547538757
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  75
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20026442
flow loss 0.056559317
occ loss 0.14338417
time for this batch 0.3498563766479492
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27336994
flow loss 0.07181041
occ loss 0.20080796
time for this batch 0.2871274948120117
----------------------------------
train loss for this epoch:  0.22978
time for this epoch 47.31728219985962
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  76
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23200454
flow loss 0.05780559
occ loss 0.17359763
time for this batch 0.24608087539672852
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16667335
flow loss 0.046726134
occ loss 0.119713694
time for this batch 0.30629634857177734
----------------------------------
train loss for this epoch:  0.228306
time for this epoch 47.5741229057312
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  77
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21628083
flow loss 0.060508426
occ loss 0.15505117
time for this batch 0.27470850944519043
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22555062
flow loss 0.064694345
occ loss 0.16044168
time for this batch 0.2881901264190674
----------------------------------
train loss for this epoch:  0.229623
time for this epoch 46.915695667266846
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  78
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27834538
flow loss 0.07392144
occ loss 0.20372245
time for this batch 0.25233030319213867
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20504577
flow loss 0.058949284
occ loss 0.14560613
time for this batch 0.30225038528442383
----------------------------------
train loss for this epoch:  0.227659
time for this epoch 46.90415620803833
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  79
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2505478
flow loss 0.06557221
occ loss 0.18446475
time for this batch 0.2692556381225586
----------------------------------
i_batch:  64.0
the loss for this batch:  0.26653948
flow loss 0.0730037
occ loss 0.19294351
time for this batch 0.2814652919769287
----------------------------------
train loss for this epoch:  0.228557
time for this epoch 47.55026125907898
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  80
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2493121
flow loss 0.06419127
occ loss 0.18470189
time for this batch 0.27361345291137695
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19995093
flow loss 0.055225525
occ loss 0.1443886
time for this batch 0.28985142707824707
----------------------------------
train loss for this epoch:  0.228305
time for this epoch 47.22338628768921
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  81
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23140326
flow loss 0.06325287
occ loss 0.16755438
time for this batch 0.2597935199737549
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23868135
flow loss 0.06451139
occ loss 0.173833
time for this batch 0.30531859397888184
----------------------------------
train loss for this epoch:  0.228037
time for this epoch 47.36562967300415
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  82
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23604919
flow loss 0.06889221
occ loss 0.1662976
time for this batch 0.2612295150756836
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19545165
flow loss 0.054126956
occ loss 0.14066163
time for this batch 0.2794487476348877
----------------------------------
train loss for this epoch:  0.228242
time for this epoch 46.55345892906189
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  83
# batch:  125
i_batch:  0.0
the loss for this batch:  0.28111106
flow loss 0.072440974
occ loss 0.20810975
time for this batch 0.2687239646911621
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27600148
flow loss 0.07044809
occ loss 0.20444429
time for this batch 0.2986612319946289
----------------------------------
train loss for this epoch:  0.226867
time for this epoch 47.11930966377258
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  84
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21470536
flow loss 0.056261625
occ loss 0.15780936
time for this batch 0.2536649703979492
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24469492
flow loss 0.0689421
occ loss 0.17518108
time for this batch 0.2734518051147461
----------------------------------
train loss for this epoch:  0.225967
time for this epoch 47.21006989479065
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  85
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26767802
flow loss 0.078819305
occ loss 0.18792738
time for this batch 0.2561836242675781
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16610686
flow loss 0.051262695
occ loss 0.11421365
time for this batch 0.2981531620025635
----------------------------------
train loss for this epoch:  0.227459
time for this epoch 47.55588746070862
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  86
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19356786
flow loss 0.057555374
occ loss 0.13554105
time for this batch 0.2684750556945801
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2145754
flow loss 0.064814776
occ loss 0.14929502
time for this batch 0.2997293472290039
----------------------------------
train loss for this epoch:  0.226646
time for this epoch 47.334171295166016
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  87
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18599808
flow loss 0.054103717
occ loss 0.13150391
time for this batch 0.2707970142364502
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2681622
flow loss 0.067158625
occ loss 0.20059426
time for this batch 0.29264235496520996
----------------------------------
train loss for this epoch:  0.225464
time for this epoch 47.42380928993225
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  88
# batch:  125
i_batch:  0.0
the loss for this batch:  0.1909822
flow loss 0.05608552
occ loss 0.13424157
time for this batch 0.2670705318450928
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23145758
flow loss 0.06371058
occ loss 0.16745135
time for this batch 0.2684352397918701
----------------------------------
train loss for this epoch:  0.226172
time for this epoch 47.32651114463806
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  89
# batch:  125
i_batch:  0.0
the loss for this batch:  0.15951857
flow loss 0.04690537
occ loss 0.11226001
time for this batch 0.26658129692077637
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24660812
flow loss 0.061599154
occ loss 0.18435436
time for this batch 0.2925376892089844
----------------------------------
train loss for this epoch:  0.22407
time for this epoch 47.55641770362854
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  90
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22472997
flow loss 0.060064077
occ loss 0.16409431
time for this batch 0.25827550888061523
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19661292
flow loss 0.05509768
occ loss 0.14096376
time for this batch 0.28626251220703125
----------------------------------
train loss for this epoch:  0.225065
time for this epoch 47.52484893798828
No_decrease:  7
----------------an epoch starts-------------------
i_epoch:  91
# batch:  125
i_batch:  0.0
the loss for this batch:  0.34697008
flow loss 0.08924756
occ loss 0.2572858
time for this batch 0.24636149406433105
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22945014
flow loss 0.06435562
occ loss 0.16447224
time for this batch 0.29666709899902344
----------------------------------
train loss for this epoch:  0.225477
time for this epoch 46.87674880027771
No_decrease:  8
----------------an epoch starts-------------------
i_epoch:  92
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20048472
flow loss 0.053577602
occ loss 0.14575236
time for this batch 0.2670106887817383
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22200595
flow loss 0.057517603
occ loss 0.16383867
time for this batch 0.28465819358825684
----------------------------------
train loss for this epoch:  0.224886
time for this epoch 47.28799223899841
No_decrease:  9
----------------an epoch starts-------------------
i_epoch:  93
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26989183
flow loss 0.07781762
occ loss 0.19145073
time for this batch 0.2622947692871094
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22913764
flow loss 0.06680572
occ loss 0.16127306
time for this batch 0.2943706512451172
----------------------------------
train loss for this epoch:  0.224196
time for this epoch 47.05207371711731
No_decrease:  10
----------------an epoch starts-------------------
i_epoch:  94
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24007244
flow loss 0.06206041
occ loss 0.17762168
time for this batch 0.25510168075561523
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2184454
flow loss 0.05619896
occ loss 0.16199675
time for this batch 0.2980616092681885
----------------------------------
train loss for this epoch:  0.224684
time for this epoch 47.52310538291931
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  95
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27375016
flow loss 0.074697755
occ loss 0.19865957
time for this batch 0.2587621212005615
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19834377
flow loss 0.06265927
occ loss 0.13507587
time for this batch 0.29793667793273926
----------------------------------
train loss for this epoch:  0.223323
time for this epoch 46.85683822631836
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  96
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17677973
flow loss 0.051996917
occ loss 0.124561496
time for this batch 0.257068395614624
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27920687
flow loss 0.07167217
occ loss 0.2068914
time for this batch 0.2996647357940674
----------------------------------
train loss for this epoch:  0.223077
time for this epoch 46.76869440078735
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  97
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23619846
flow loss 0.06622104
occ loss 0.16960652
time for this batch 0.25528931617736816
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22709352
flow loss 0.06184226
occ loss 0.16483621
time for this batch 0.307098388671875
----------------------------------
train loss for this epoch:  0.224456
time for this epoch 47.020057678222656
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  98
# batch:  125
i_batch:  0.0
the loss for this batch:  0.15823515
flow loss 0.04512996
occ loss 0.11255169
time for this batch 0.25237226486206055
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22814828
flow loss 0.06662852
occ loss 0.16091661
time for this batch 0.27634358406066895
----------------------------------
train loss for this epoch:  0.223944
time for this epoch 46.975518465042114
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  99
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21167402
flow loss 0.059908684
occ loss 0.15146658
time for this batch 0.2670915126800537
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2242257
flow loss 0.063878305
occ loss 0.15976354
time for this batch 0.30036401748657227
----------------------------------
train loss for this epoch:  0.223027
time for this epoch 47.68540287017822
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  100
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24973303
flow loss 0.059866983
occ loss 0.18911374
time for this batch 0.26645421981811523
----------------------------------
i_batch:  64.0
the loss for this batch:  0.1971277
flow loss 0.06095229
occ loss 0.135418
time for this batch 0.29178929328918457
----------------------------------
train loss for this epoch:  0.224301
time for this epoch 47.20949149131775
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  101
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23962826
flow loss 0.06150442
occ loss 0.17742729
time for this batch 0.25769662857055664
----------------------------------
i_batch:  64.0
the loss for this batch:  0.15409818
flow loss 0.04741452
occ loss 0.10632665
time for this batch 0.28556203842163086
----------------------------------
train loss for this epoch:  0.222586
time for this epoch 47.15072011947632
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  102
# batch:  125
i_batch:  0.0
the loss for this batch:  0.15467055
flow loss 0.046791315
occ loss 0.107619084
time for this batch 0.2750985622406006
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18649942
flow loss 0.051912438
occ loss 0.13397431
time for this batch 0.2899799346923828
----------------------------------
train loss for this epoch:  0.222217
time for this epoch 47.02670431137085
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  103
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23399526
flow loss 0.060445625
occ loss 0.17302832
time for this batch 0.25742340087890625
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25926605
flow loss 0.06807922
occ loss 0.1907323
time for this batch 0.2941014766693115
----------------------------------
train loss for this epoch:  0.222438
time for this epoch 47.382933616638184
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  104
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22540803
flow loss 0.06217406
occ loss 0.16271056
time for this batch 0.2613379955291748
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18226808
flow loss 0.05415452
occ loss 0.12772079
time for this batch 0.30111217498779297
----------------------------------
train loss for this epoch:  0.220787
time for this epoch 46.63507866859436
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  105
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18235563
flow loss 0.05128048
occ loss 0.13045818
time for this batch 0.272763729095459
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25873244
flow loss 0.070794046
occ loss 0.18720824
time for this batch 0.29265713691711426
----------------------------------
train loss for this epoch:  0.220799
time for this epoch 46.53801250457764
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  106
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23151481
flow loss 0.06514883
occ loss 0.16575769
time for this batch 0.2507011890411377
----------------------------------
i_batch:  64.0
the loss for this batch:  0.28969324
flow loss 0.07104124
occ loss 0.21786486
time for this batch 0.2954566478729248
----------------------------------
train loss for this epoch:  0.221814
time for this epoch 46.81429696083069
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  107
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27902168
flow loss 0.07170975
occ loss 0.20690091
time for this batch 0.23834609985351562
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21348573
flow loss 0.060039807
occ loss 0.15297793
time for this batch 0.30982398986816406
----------------------------------
train loss for this epoch:  0.220691
time for this epoch 46.36823391914368
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  108
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18806933
flow loss 0.056069244
occ loss 0.13152705
time for this batch 0.25530481338500977
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19742467
flow loss 0.055862688
occ loss 0.14109188
time for this batch 0.27718091011047363
----------------------------------
train loss for this epoch:  0.222094
time for this epoch 47.07396411895752
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  109
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19742267
flow loss 0.05692082
occ loss 0.1401186
time for this batch 0.26055407524108887
----------------------------------
i_batch:  64.0
the loss for this batch:  0.13255581
flow loss 0.040006444
occ loss 0.09161787
time for this batch 0.2845637798309326
----------------------------------
train loss for this epoch:  0.221785
time for this epoch 46.559916496276855
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  110
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2917515
flow loss 0.07083675
occ loss 0.22052361
time for this batch 0.2646162509918213
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24006897
flow loss 0.063179545
occ loss 0.17622955
time for this batch 0.2922067642211914
----------------------------------
train loss for this epoch:  0.221
time for this epoch 47.83486890792847
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  111
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21231051
flow loss 0.058298107
occ loss 0.1534221
time for this batch 0.2695333957672119
----------------------------------
i_batch:  64.0
the loss for this batch:  0.17765418
flow loss 0.048610426
occ loss 0.12837256
time for this batch 0.2981088161468506
----------------------------------
train loss for this epoch:  0.219739
time for this epoch 47.25558567047119
No_decrease:  7
----------------an epoch starts-------------------
i_epoch:  112
# batch:  125
i_batch:  0.0
the loss for this batch:  0.29169002
flow loss 0.08190335
occ loss 0.20939149
time for this batch 0.2591419219970703
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23999743
flow loss 0.067132264
occ loss 0.17251933
time for this batch 0.2809288501739502
----------------------------------
train loss for this epoch:  0.221125
time for this epoch 47.2586829662323
No_decrease:  8
----------------an epoch starts-------------------
i_epoch:  113
# batch:  125
i_batch:  0.0
the loss for this batch:  0.27344596
flow loss 0.07202513
occ loss 0.20090409
time for this batch 0.26323461532592773
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22564581
flow loss 0.058969002
occ loss 0.16609828
time for this batch 0.3000969886779785
----------------------------------
train loss for this epoch:  0.219412
time for this epoch 47.52973031997681
No_decrease:  9
----------------an epoch starts-------------------
i_epoch:  114
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20141241
flow loss 0.057376176
occ loss 0.14371713
time for this batch 0.2289109230041504
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16331281
flow loss 0.04827935
occ loss 0.11438498
time for this batch 0.281569242477417
----------------------------------
train loss for this epoch:  0.219969
time for this epoch 47.42804718017578
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  115
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18093707
flow loss 0.057023883
occ loss 0.12360453
time for this batch 0.2786571979522705
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25064263
flow loss 0.063117474
occ loss 0.18712452
time for this batch 0.30254554748535156
----------------------------------
train loss for this epoch:  0.218985
time for this epoch 46.257829666137695
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  116
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18182087
flow loss 0.055429623
occ loss 0.12591058
time for this batch 0.25534677505493164
----------------------------------
i_batch:  64.0
the loss for this batch:  0.29770887
flow loss 0.07634772
occ loss 0.22092253
time for this batch 0.30246591567993164
----------------------------------
train loss for this epoch:  0.219443
time for this epoch 47.03590130805969
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  117
# batch:  125
i_batch:  0.0
the loss for this batch:  0.137828
flow loss 0.04458708
occ loss 0.09291511
time for this batch 0.2641575336456299
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23416035
flow loss 0.066887625
occ loss 0.16673365
time for this batch 0.27777624130249023
----------------------------------
train loss for this epoch:  0.219482
time for this epoch 47.74198269844055
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  118
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20627113
flow loss 0.057425663
occ loss 0.1466743
time for this batch 0.29274821281433105
----------------------------------
i_batch:  64.0
the loss for this batch:  0.17514564
flow loss 0.05415994
occ loss 0.12062561
time for this batch 0.2958528995513916
----------------------------------
train loss for this epoch:  0.219502
time for this epoch 47.68229532241821
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  119
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19610979
flow loss 0.04946136
occ loss 0.14590828
time for this batch 0.25638461112976074
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18806085
flow loss 0.05620066
occ loss 0.13136922
time for this batch 0.2900676727294922
----------------------------------
train loss for this epoch:  0.219702
time for this epoch 47.07689905166626
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  120
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22200584
flow loss 0.058634035
occ loss 0.1628272
time for this batch 0.2734682559967041
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21803288
flow loss 0.0631919
occ loss 0.15445563
time for this batch 0.25345849990844727
----------------------------------
train loss for this epoch:  0.218533
time for this epoch 47.934553146362305
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  121
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2191689
flow loss 0.059665002
occ loss 0.15877832
time for this batch 0.28266263008117676
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19132972
flow loss 0.06044713
occ loss 0.13046
time for this batch 0.311748743057251
----------------------------------
train loss for this epoch:  0.219383
time for this epoch 47.13943672180176
No_decrease:  7
----------------an epoch starts-------------------
i_epoch:  122
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25493687
flow loss 0.06701924
occ loss 0.18761837
time for this batch 0.2505645751953125
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24063185
flow loss 0.06356003
occ loss 0.17645353
time for this batch 0.2849719524383545
----------------------------------
train loss for this epoch:  0.219705
time for this epoch 47.135721921920776
No_decrease:  8
----------------an epoch starts-------------------
i_epoch:  123
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24890995
flow loss 0.06884228
occ loss 0.1794167
time for this batch 0.2568776607513428
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19091994
flow loss 0.057308834
occ loss 0.13336346
time for this batch 0.3012351989746094
----------------------------------
train loss for this epoch:  0.218296
time for this epoch 46.95341157913208
No_decrease:  9
----------------an epoch starts-------------------
i_epoch:  124
# batch:  125
i_batch:  0.0
the loss for this batch:  0.1942326
flow loss 0.056310415
occ loss 0.13746749
time for this batch 0.27208995819091797
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22632639
flow loss 0.08222665
occ loss 0.14301272
time for this batch 0.2944605350494385
----------------------------------
train loss for this epoch:  0.222706
time for this epoch 48.3430438041687
No_decrease:  10
----------------an epoch starts-------------------
i_epoch:  125
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18086606
flow loss 0.049726184
occ loss 0.13041596
time for this batch 0.2680931091308594
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27108976
flow loss 0.06777339
occ loss 0.20284988
time for this batch 0.2963564395904541
----------------------------------
train loss for this epoch:  0.217301
time for this epoch 47.73315095901489
No_decrease:  11
----------------an epoch starts-------------------
i_epoch:  126
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24381572
flow loss 0.06806336
occ loss 0.17519939
time for this batch 0.25179338455200195
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20206064
flow loss 0.051935032
occ loss 0.14967956
time for this batch 0.2917478084564209
----------------------------------
train loss for this epoch:  0.216874
time for this epoch 47.798412799835205
No_decrease:  12
----------------an epoch starts-------------------
i_epoch:  127
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25494295
flow loss 0.06772278
occ loss 0.18687436
time for this batch 0.2470531463623047
----------------------------------
i_batch:  64.0
the loss for this batch:  0.3097865
flow loss 0.08125269
occ loss 0.22807676
time for this batch 0.27557826042175293
----------------------------------
train loss for this epoch:  0.217544
time for this epoch 47.4901180267334
No_decrease:  13
----------------an epoch starts-------------------
i_epoch:  128
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21407175
flow loss 0.060442757
occ loss 0.15320736
time for this batch 0.26371216773986816
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22686146
flow loss 0.060660727
occ loss 0.16557744
time for this batch 0.2957170009613037
----------------------------------
train loss for this epoch:  0.217229
time for this epoch 47.67625665664673
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  129
# batch:  125
i_batch:  0.0
the loss for this batch:  0.28906953
flow loss 0.07641371
occ loss 0.21203063
time for this batch 0.27312564849853516
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21574385
flow loss 0.060117442
occ loss 0.15532373
time for this batch 0.28853869438171387
----------------------------------
train loss for this epoch:  0.217226
time for this epoch 46.783326148986816
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  130
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23663773
flow loss 0.062352233
occ loss 0.17367063
time for this batch 0.26282596588134766
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24551424
flow loss 0.068652056
occ loss 0.17652288
time for this batch 0.2981224060058594
----------------------------------
train loss for this epoch:  0.217464
time for this epoch 47.159279346466064
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  131
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24094765
flow loss 0.06359128
occ loss 0.17682713
time for this batch 0.23296904563903809
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23442681
flow loss 0.065042235
occ loss 0.16868311
time for this batch 0.2895796298980713
----------------------------------
train loss for this epoch:  0.217065
time for this epoch 47.42090559005737
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  132
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24343115
flow loss 0.06049733
occ loss 0.18245104
time for this batch 0.2698979377746582
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2860859
flow loss 0.07262067
occ loss 0.21295094
time for this batch 0.30417776107788086
----------------------------------
train loss for this epoch:  0.217734
time for this epoch 46.61857461929321
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  133
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19150177
flow loss 0.055533618
occ loss 0.1354183
time for this batch 0.2515866756439209
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21237203
flow loss 0.057910956
occ loss 0.15379405
time for this batch 0.2862966060638428
----------------------------------
train loss for this epoch:  0.218796
time for this epoch 47.555232524871826
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  134
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2832797
flow loss 0.06971473
occ loss 0.21291472
time for this batch 0.22903823852539062
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21771365
flow loss 0.055280354
occ loss 0.16176465
time for this batch 0.30055689811706543
----------------------------------
train loss for this epoch:  0.21592
time for this epoch 47.08804678916931
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  135
# batch:  125
i_batch:  0.0
the loss for this batch:  0.1714489
flow loss 0.047168158
occ loss 0.12388081
time for this batch 0.2606794834136963
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19015616
flow loss 0.055162027
occ loss 0.13471241
time for this batch 0.2975146770477295
----------------------------------
train loss for this epoch:  0.218441
time for this epoch 48.16963982582092
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  136
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23863824
flow loss 0.06336951
occ loss 0.174927
time for this batch 0.26873111724853516
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18926926
flow loss 0.057131644
occ loss 0.13148463
time for this batch 0.2895185947418213
----------------------------------
train loss for this epoch:  0.216741
time for this epoch 47.881932973861694
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  137
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18138586
flow loss 0.05174737
occ loss 0.12935154
time for this batch 0.2786080837249756
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2865008
flow loss 0.069707714
occ loss 0.21624604
time for this batch 0.2628183364868164
----------------------------------
train loss for this epoch:  0.215972
time for this epoch 46.26638650894165
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  138
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2184561
flow loss 0.059811138
occ loss 0.15834703
time for this batch 0.2605397701263428
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19247743
flow loss 0.054656785
occ loss 0.13748923
time for this batch 0.2760031223297119
----------------------------------
train loss for this epoch:  0.21573
time for this epoch 47.09421467781067
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  139
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2587137
flow loss 0.0709266
occ loss 0.1871278
time for this batch 0.23897886276245117
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21398732
flow loss 0.062047906
occ loss 0.15109289
time for this batch 0.30007171630859375
----------------------------------
train loss for this epoch:  0.21603
time for this epoch 47.498694896698
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  140
# batch:  125
i_batch:  0.0
the loss for this batch:  0.13423513
flow loss 0.040231153
occ loss 0.0936144
time for this batch 0.27071261405944824
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21943593
flow loss 0.058191225
occ loss 0.1608055
time for this batch 0.2946968078613281
----------------------------------
train loss for this epoch:  0.216014
time for this epoch 47.295650243759155
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  141
# batch:  125
i_batch:  0.0
the loss for this batch:  0.15996872
flow loss 0.047252495
occ loss 0.11235078
time for this batch 0.283494234085083
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21580355
flow loss 0.058304362
occ loss 0.15717565
time for this batch 0.29706478118896484
----------------------------------
train loss for this epoch:  0.216289
time for this epoch 46.985618591308594
No_decrease:  7
----------------an epoch starts-------------------
i_epoch:  142
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26205006
flow loss 0.066241875
occ loss 0.1954116
time for this batch 0.26685261726379395
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18488818
flow loss 0.051683094
occ loss 0.13285
time for this batch 0.29510498046875
----------------------------------
train loss for this epoch:  0.21517
time for this epoch 47.459959745407104
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  143
# batch:  125
i_batch:  0.0
the loss for this batch:  0.15351094
flow loss 0.04612854
occ loss 0.107108034
time for this batch 0.2781643867492676
----------------------------------
i_batch:  64.0
the loss for this batch:  0.27597365
flow loss 0.07131522
occ loss 0.20379542
time for this batch 0.30126166343688965
----------------------------------
train loss for this epoch:  0.215707
time for this epoch 46.75617218017578
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  144
# batch:  125
i_batch:  0.0
the loss for this batch:  0.16967164
flow loss 0.04438633
occ loss 0.12429821
time for this batch 0.271148681640625
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21554504
flow loss 0.061100177
occ loss 0.15413792
time for this batch 0.2776041030883789
----------------------------------
train loss for this epoch:  0.21681
time for this epoch 47.2680549621582
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  145
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22468543
flow loss 0.062223434
occ loss 0.16209649
time for this batch 0.18397212028503418
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19971019
flow loss 0.05595283
occ loss 0.14334254
time for this batch 0.30547046661376953
----------------------------------
train loss for this epoch:  0.215279
time for this epoch 47.45968055725098
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  146
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2626447
flow loss 0.06555498
occ loss 0.19653267
time for this batch 0.27297425270080566
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24557774
flow loss 0.06548678
occ loss 0.17961445
time for this batch 0.2568628787994385
----------------------------------
train loss for this epoch:  0.216027
time for this epoch 43.04589533805847
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  147
# batch:  125
i_batch:  0.0
the loss for this batch:  0.31037328
flow loss 0.072889775
occ loss 0.23669554
time for this batch 0.2297370433807373
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21295089
flow loss 0.0629737
occ loss 0.14955696
time for this batch 0.2725965976715088
----------------------------------
train loss for this epoch:  0.215039
time for this epoch 42.96318769454956
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  148
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18947263
flow loss 0.05348306
occ loss 0.13569732
time for this batch 0.20957732200622559
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20614737
flow loss 0.054906465
occ loss 0.15087566
time for this batch 0.2771327495574951
----------------------------------
train loss for this epoch:  0.215551
time for this epoch 41.0017511844635
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  149
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21346624
flow loss 0.058393594
occ loss 0.1547935
time for this batch 0.23520708084106445
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19492403
flow loss 0.055638794
occ loss 0.13865758
time for this batch 0.26777148246765137
----------------------------------
train loss for this epoch:  0.21494
time for this epoch 40.32922840118408
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  150
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2650012
flow loss 0.06592083
occ loss 0.19845401
time for this batch 0.20517492294311523
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18652774
flow loss 0.052242838
occ loss 0.13392787
time for this batch 0.2598299980163574
----------------------------------
train loss for this epoch:  0.20845
time for this epoch 40.6515531539917
No_decrease:  0
----------------an epoch starts-------------------
i_epoch:  151
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21832016
flow loss 0.05495089
occ loss 0.16296105
time for this batch 0.19799113273620605
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2223007
flow loss 0.057496794
occ loss 0.1643562
time for this batch 0.24366450309753418
----------------------------------
train loss for this epoch:  0.207457
time for this epoch 40.1722366809845
No_decrease:  1
----------------an epoch starts-------------------
i_epoch:  152
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2584956
flow loss 0.06951432
occ loss 0.18856917
time for this batch 0.19930386543273926
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2182394
flow loss 0.056593727
occ loss 0.16115071
time for this batch 0.26369595527648926
----------------------------------
train loss for this epoch:  0.206302
time for this epoch 41.328067779541016
No_decrease:  2
----------------an epoch starts-------------------
i_epoch:  153
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20626646
flow loss 0.06032289
occ loss 0.14561778
time for this batch 0.2114100456237793
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20724377
flow loss 0.055035625
occ loss 0.15191664
time for this batch 0.2182612419128418
----------------------------------
train loss for this epoch:  0.206471
time for this epoch 36.533257722854614
No_decrease:  3
----------------an epoch starts-------------------
i_epoch:  154
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23340899
flow loss 0.06528624
occ loss 0.16760686
time for this batch 0.20197224617004395
----------------------------------
i_batch:  64.0
the loss for this batch:  0.21805769
flow loss 0.05807702
occ loss 0.1596145
time for this batch 0.2395472526550293
----------------------------------
train loss for this epoch:  0.206819
time for this epoch 38.30153965950012
No_decrease:  4
----------------an epoch starts-------------------
i_epoch:  155
# batch:  125
i_batch:  0.0
the loss for this batch:  0.26771277
flow loss 0.06677699
occ loss 0.20052223
time for this batch 0.20337986946105957
----------------------------------
i_batch:  64.0
the loss for this batch:  0.24591903
flow loss 0.06180777
occ loss 0.18374394
time for this batch 0.26564908027648926
----------------------------------
train loss for this epoch:  0.206545
time for this epoch 40.455445528030396
No_decrease:  5
----------------an epoch starts-------------------
i_epoch:  156
# batch:  125
i_batch:  0.0
the loss for this batch:  0.25931358
flow loss 0.063069426
occ loss 0.19582438
time for this batch 0.2645440101623535
----------------------------------
i_batch:  64.0
the loss for this batch:  0.2185557
flow loss 0.060834862
occ loss 0.15721765
time for this batch 0.260089635848999
----------------------------------
train loss for this epoch:  0.206513
time for this epoch 41.4960401058197
No_decrease:  6
----------------an epoch starts-------------------
i_epoch:  157
# batch:  125
i_batch:  0.0
the loss for this batch:  0.23159291
flow loss 0.062200174
occ loss 0.16903917
time for this batch 0.21068143844604492
----------------------------------
i_batch:  64.0
the loss for this batch:  0.15574284
flow loss 0.04433285
occ loss 0.11110937
time for this batch 0.2600581645965576
----------------------------------
train loss for this epoch:  0.206523
time for this epoch 41.37224745750427
No_decrease:  7
----------------an epoch starts-------------------
i_epoch:  158
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18698826
flow loss 0.051358406
occ loss 0.13536468
time for this batch 0.23157620429992676
----------------------------------
i_batch:  64.0
the loss for this batch:  0.26634187
flow loss 0.07185249
occ loss 0.19406308
time for this batch 0.23673105239868164
----------------------------------
train loss for this epoch:  0.206613
time for this epoch 39.641467571258545
No_decrease:  8
----------------an epoch starts-------------------
i_epoch:  159
# batch:  125
i_batch:  0.0
the loss for this batch:  0.12973377
flow loss 0.041348904
occ loss 0.088110164
time for this batch 0.21560239791870117
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19860072
flow loss 0.055671062
occ loss 0.14268817
time for this batch 0.26464343070983887
----------------------------------
train loss for this epoch:  0.206445
time for this epoch 41.35438585281372
No_decrease:  9
----------------an epoch starts-------------------
i_epoch:  160
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18185477
flow loss 0.05018213
occ loss 0.13144426
time for this batch 0.15895605087280273
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16294473
flow loss 0.044129964
occ loss 0.11846012
time for this batch 0.20165467262268066
----------------------------------
train loss for this epoch:  0.206113
time for this epoch 41.988266944885254
No_decrease:  10
----------------an epoch starts-------------------
i_epoch:  161
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17527081
flow loss 0.048129216
occ loss 0.12680309
time for this batch 0.23383784294128418
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22511855
flow loss 0.061881833
occ loss 0.16261823
time for this batch 0.2552330493927002
----------------------------------
train loss for this epoch:  0.206399
time for this epoch 40.80246019363403
No_decrease:  11
----------------an epoch starts-------------------
i_epoch:  162
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2203226
flow loss 0.05723025
occ loss 0.16282006
time for this batch 0.15674376487731934
----------------------------------
i_batch:  64.0
the loss for this batch:  0.15136266
flow loss 0.046818107
occ loss 0.10431208
time for this batch 0.2350156307220459
----------------------------------
train loss for this epoch:  0.206084
time for this epoch 39.95799803733826
No_decrease:  12
----------------an epoch starts-------------------
i_epoch:  163
# batch:  125
i_batch:  0.0
the loss for this batch:  0.16990283
flow loss 0.04811989
occ loss 0.12147142
time for this batch 0.22716331481933594
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20145062
flow loss 0.056037873
occ loss 0.1451184
time for this batch 0.23952221870422363
----------------------------------
train loss for this epoch:  0.206061
time for this epoch 41.36119079589844
No_decrease:  13
----------------an epoch starts-------------------
i_epoch:  164
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17456132
flow loss 0.056322545
occ loss 0.1178682
time for this batch 0.1961066722869873
----------------------------------
i_batch:  64.0
the loss for this batch:  0.26600003
flow loss 0.0706007
occ loss 0.1950615
time for this batch 0.2719240188598633
----------------------------------
train loss for this epoch:  0.205913
time for this epoch 40.808897495269775
No_decrease:  14
----------------an epoch starts-------------------
i_epoch:  165
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21899644
flow loss 0.058634043
occ loss 0.1600853
time for this batch 0.23692941665649414
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16579236
flow loss 0.045831002
occ loss 0.11961085
time for this batch 0.27388834953308105
----------------------------------
train loss for this epoch:  0.206217
time for this epoch 41.22698378562927
No_decrease:  15
----------------an epoch starts-------------------
i_epoch:  166
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20885094
flow loss 0.056882013
occ loss 0.15152061
time for this batch 0.21873760223388672
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23038949
flow loss 0.057549156
occ loss 0.17226219
time for this batch 0.2722768783569336
----------------------------------
train loss for this epoch:  0.205718
time for this epoch 41.53787112236023
No_decrease:  16
----------------an epoch starts-------------------
i_epoch:  167
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17017916
flow loss 0.04673846
occ loss 0.12309806
time for this batch 0.21821379661560059
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23251389
flow loss 0.05742092
occ loss 0.17469952
time for this batch 0.2789011001586914
----------------------------------
train loss for this epoch:  0.205897
time for this epoch 41.089350938797
No_decrease:  17
----------------an epoch starts-------------------
i_epoch:  168
# batch:  125
i_batch:  0.0
the loss for this batch:  0.1731047
flow loss 0.04883546
occ loss 0.12393721
time for this batch 0.19205737113952637
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22066103
flow loss 0.0582116
occ loss 0.16188936
time for this batch 0.2479252815246582
----------------------------------
train loss for this epoch:  0.205674
time for this epoch 41.29987168312073
No_decrease:  18
----------------an epoch starts-------------------
i_epoch:  169
# batch:  125
i_batch:  0.0
the loss for this batch:  0.14919363
flow loss 0.042612646
occ loss 0.10623901
time for this batch 0.2384960651397705
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25613397
flow loss 0.06316508
occ loss 0.19237769
time for this batch 0.22958111763000488
----------------------------------
train loss for this epoch:  0.205696
time for this epoch 40.368603229522705
No_decrease:  19
----------------an epoch starts-------------------
i_epoch:  170
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18986031
flow loss 0.05398669
occ loss 0.13559859
time for this batch 0.22502970695495605
----------------------------------
i_batch:  64.0
the loss for this batch:  0.12513039
flow loss 0.038568143
occ loss 0.08633053
time for this batch 0.23203468322753906
----------------------------------
train loss for this epoch:  0.205677
time for this epoch 39.80390691757202
No_decrease:  20
----------------an epoch starts-------------------
i_epoch:  171
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17501144
flow loss 0.047059365
occ loss 0.12763153
time for this batch 0.19309353828430176
----------------------------------
i_batch:  64.0
the loss for this batch:  0.25352705
flow loss 0.06460174
occ loss 0.1883572
time for this batch 0.27330636978149414
----------------------------------
train loss for this epoch:  0.205906
time for this epoch 41.107749700546265
No_decrease:  21
----------------an epoch starts-------------------
i_epoch:  172
# batch:  125
i_batch:  0.0
the loss for this batch:  0.24074893
flow loss 0.068971716
occ loss 0.17125596
time for this batch 0.2523798942565918
----------------------------------
i_batch:  64.0
the loss for this batch:  0.20906834
flow loss 0.059029896
occ loss 0.14968686
time for this batch 0.2816154956817627
----------------------------------
train loss for this epoch:  0.205312
time for this epoch 41.683329820632935
No_decrease:  22
----------------an epoch starts-------------------
i_epoch:  173
# batch:  125
i_batch:  0.0
the loss for this batch:  0.17736349
flow loss 0.05118203
occ loss 0.1259411
time for this batch 0.23881030082702637
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19436261
flow loss 0.053372502
occ loss 0.14072385
time for this batch 0.2540004253387451
----------------------------------
train loss for this epoch:  0.205558
time for this epoch 40.00807571411133
No_decrease:  23
----------------an epoch starts-------------------
i_epoch:  174
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2129353
flow loss 0.055335198
occ loss 0.15706316
time for this batch 0.2583446502685547
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16701527
flow loss 0.04971849
occ loss 0.116997965
time for this batch 0.25382256507873535
----------------------------------
train loss for this epoch:  0.205757
time for this epoch 41.2247896194458
No_decrease:  24
----------------an epoch starts-------------------
i_epoch:  175
# batch:  125
i_batch:  0.0
the loss for this batch:  0.18363215
flow loss 0.0556709
occ loss 0.12765455
time for this batch 0.2131640911102295
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19202879
flow loss 0.057532594
occ loss 0.13420253
time for this batch 0.2504408359527588
----------------------------------
train loss for this epoch:  0.205499
time for this epoch 39.81772208213806
No_decrease:  25
----------------an epoch starts-------------------
i_epoch:  176
# batch:  125
i_batch:  0.0
the loss for this batch:  0.19227134
flow loss 0.051590644
occ loss 0.1401833
time for this batch 0.2418968677520752
----------------------------------
i_batch:  64.0
the loss for this batch:  0.16841443
flow loss 0.048155714
occ loss 0.11987661
time for this batch 0.2654738426208496
----------------------------------
train loss for this epoch:  0.205523
time for this epoch 40.44121217727661
No_decrease:  26
----------------an epoch starts-------------------
i_epoch:  177
# batch:  125
i_batch:  0.0
the loss for this batch:  0.20141819
flow loss 0.05632822
occ loss 0.14465709
time for this batch 0.19767141342163086
----------------------------------
i_batch:  64.0
the loss for this batch:  0.18843658
flow loss 0.054312862
occ loss 0.13392574
time for this batch 0.2526674270629883
----------------------------------
train loss for this epoch:  0.205271
time for this epoch 41.15841507911682
No_decrease:  27
----------------an epoch starts-------------------
i_epoch:  178
# batch:  125
i_batch:  0.0
the loss for this batch:  0.2154789
flow loss 0.059528172
occ loss 0.15569629
time for this batch 0.2210979461669922
----------------------------------
i_batch:  64.0
the loss for this batch:  0.22521336
flow loss 0.061221283
occ loss 0.16358265
time for this batch 0.26985740661621094
----------------------------------
train loss for this epoch:  0.20514
time for this epoch 41.647724866867065
No_decrease:  28
----------------an epoch starts-------------------
i_epoch:  179
# batch:  125
i_batch:  0.0
the loss for this batch:  0.21368484
flow loss 0.055513304
occ loss 0.15779634
time for this batch 0.20692896842956543
----------------------------------
i_batch:  64.0
the loss for this batch:  0.23669542
flow loss 0.06649097
occ loss 0.16990575
time for this batch 0.25688934326171875
----------------------------------
train loss for this epoch:  0.205392
time for this epoch 40.62503910064697
No_decrease:  29
----------------an epoch starts-------------------
i_epoch:  180
# batch:  125
i_batch:  0.0
the loss for this batch:  0.22305347
flow loss 0.05948866
occ loss 0.16327912
time for this batch 0.24269723892211914
----------------------------------
i_batch:  64.0
the loss for this batch:  0.19205001
flow loss 0.054287605
occ loss 0.13735195
time for this batch 0.2603893280029297
----------------------------------
train loss for this epoch:  0.205328
time for this epoch 41.539491415023804
Early stop at the 181-th epoch

7: apply the model to vali and test¶

In [13]:
def apply_to_vali_test(model, vt, f_o_mean_std):
    f = vt["flow"]
    f_m = vt["flow_mask"].to(device)
    o = vt["occupancy"]
    o_m = vt["occupancy_mask"].to(device)
    f_mae, f_rmse, o_mae, o_rmse  = vali_test(model, f, f_m, o, o_m, f_o_mean_std, hyper["b_s_vt"])
    print ("flow_mae", f_mae)
    print ("flow_rmse", f_rmse)
    print ("occ_mae", o_mae)
    print ("occ_rmse", o_rmse)
    return f_mae, f_rmse, o_mae, o_rmse

Validate¶

In [14]:
vali_f_mae, vali_f_rmse, vali_o_mae, vali_o_rmse =\
    apply_to_vali_test(trained_model, vali, f_o_mean_std)
flow_mae 35.79439089914421
flow_rmse 55.05386218850903
occ_mae 0.0392215118683922
occ_rmse 0.08028854952676243

Test¶

In [15]:
test_f_mae, test_f_rmse, test_o_mae, test_o_rmse =\
    apply_to_vali_test(trained_model, test, f_o_mean_std)
flow_mae 33.85003701170569
flow_rmse 52.30893986700123
occ_mae 0.032333377308166586
occ_rmse 0.06913925713477638
In [ ]:
 
In [ ]:
 
In [ ]: